Transform the future of autonomous workflows with Equifax as an AI Evaluation and Tuning Engineer in Toronto. Your expertise will ensure the reliability and performance of multi-agent systems in a full-time role.

This position focuses on enhancing the capabilities of autonomous workflows within Equifax’s cutting-edge environment. As a key player, you will evaluate Large Language Models (LLMs) to develop robust evaluation frameworks, ensuring agents maintain accuracy and minimize errors. You will collaborate closely with developers, optimize workflows, and implement guardrails to protect systems in production.

Key Responsibilities:
• Curate and maintain high-quality reference datasets for testing
• Automate evaluation pipelines for agent performance metrics




• Analyze agent decision-making processes for improvements
• Optimize interactions with external APIs and RPA workflows
• Monitor deployed agents to mitigate drift and hallucinations

Requirements:
• 3+ years in software quality engineering or ML engineering
• Hands-on experience with LLM orchestration frameworks
• Strong skills in JSON schema design and function calling
• Proficient in automated testing and debugging
• Familiarity with Python and observability platforms

Leverage your skills to enhance Equifax's AI systems as an Evaluation and Tuning Engineer.
#J-18808-Ljbffr

📌 AI Evaluation and Tuning Engineer at Equifax (Ontario)
🏢 Equifax
📍 Ontario